© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 16928
    Prev
    Next
    INDEX
    Explanations

    words related to monarchy, rulership, and succession

    oai_token-act-pair · gpt-3.5-turbo

    references to thrones and royal succession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morse
    -0.76
    velength
    -0.73
    aturdays
    -0.71
    ATIONAL
    -0.70
     Johann
    -0.68
    href
    -0.68
    anwhile
    -0.68
     Ging
    -0.68
     Greenberg
    -0.67
     Rossi
    -0.66
    POSITIVE LOGITS
     throne
    1.22
     Throne
    0.92
    pole
    0.91
    holder
    0.88
     flush
    0.84
     coffers
    0.81
    holders
    0.80
     crowned
    0.79
     holder
    0.78
    olicy
    0.77
    Activations Density 0.010%

    No Known Activations